Operators often see groups of wells (field/unit/route) as profitable while subsets quietly lose money—masked by aggregated views, declining production, flat pricing, rising LOE, and forward financials limited to twice a year.

Manual allocation of production & expenses takes weeks or months, so detailed analysis gets delayed or skipped.

What if you could automate it and get true well-level daily cashflow visibility—instant forecasts, targets, and alerts?

This educational live webinar where Casey Patterson (Founder & CEO of Avenirre, formerly XTO Energy) explores the challenge and demonstrates a practical approach built by former XTO and EOG upstream professionals.

You'll discover:

• Why aggregated economics hide underperforming wells and recurring losses
• How automation delivers well-level forward cashflow forecasts and alerts—without weeks of manual work
• Key signals: negative cashflow wells, volume shortfalls, LOE variances/overages, underpayments
• Real-world case studies (shown live by Casey, naming operators) with clear outcomes from addressing these issues
• Benefits of consolidated data, forecasting, and visibility for proactive decisions

How Measured, Verified Data Is Reshaping Global Energy Markets

In this episode of The Empirical Energy Podcast, host Mark Smith is joined by David Conley, Co-Founder of CleanConnect.ai, for a deep dive into how empirical AI is transforming the energy industry from the ground up.

They explore how Clean Connect’s platform combines direct measurement, first-principles engineering, AI, and blockchain to replace emission factors with verifiable truth—creating a flexible, auditable system for modern energy production, sustainability reporting, and trading.

This conversation goes beyond theory, featuring real-world case studies from some of the world’s largest energy producers. Mark and David unpack how empirical data is driving measurable ROI across operations, emissions management, safety, and production optimization, while unlocking new premium markets for verified energy.

You’ll also hear how multi-certification frameworks like Prove Zero, blockchain-based Energy Attribute Certificates (EACs), and partnerships with global energy traders such as Gunvor are enabling new energy products tailored for hyperscalers, AI data centers, and global buyers.

From methane mitigation and remote operations to AI-driven orchestration layers and direct combustion measurement, this episode reveals why measured and verified energy is no longer optional—it’s becoming the gold standard.

🎧 Whether you’re an energy producer, trader, operator, or technology leader, this episode offers a clear look at where the industry is heading—and how to prepare for what’s next.

00:00 – Blockchain trading and the origins of empirical verification 00:03 – Why Clean Connect became a source of truth in noisy data environments 00:12 – Moving from emission factors to first-principles measurement 00:30 – Crew Zero and direct measurement at the source 00:37 – Project Vulcan and real-time combustion measurement 01:02 – Why energy and AI are now inseparable 01:45 – Welcome to The Empirical Energy Podcast 02:03 – Global market trends shaping the future of energy 02:45 – Introducing Empirical.ai: the AI operating system for energy 03:30 – Real client case studies and measurable ROI 03:45 – The evolution of Clean Connect beyond methane mitigation 04:56 – Operations, sustainability, and market-driven outcomes 08:12 – Restoring trust through empirical data 09:18 – Integrating operations, sustainability, and trading 10:26 – Highlights from the Empirical Energy Conference 11:03 – Client feedback and new product innovation 12:09 – Remote operations, safety, and workforce augmentation 14:00 – The Integrated Operations Center explained 19:22 – Solving the data integration problem at scale 20:47 – Prove Zero and multi-certification flexibility 25:06 – Overcoming data complexity with first principles 29:08 – Partnerships, hyperscalers, and new energy markets 32:13 – Blockchain-enabled trading and Energy Attribute Certificates 33:10 – The future of empirical energy 35:01 – Final thoughts and call to action

🎙️ Revolutionizing Gas Leak Detection with Visual AI & Machine Learning

In this episode of The Empirical Energy Podcast, host Mark Smith sits down with Jae Yoon Chung, Machine Learning Engineer at Clean Connect, to explore how visual AI is transforming gas leak detection in the energy industry.

Jae breaks down the real-world challenges of detecting methane and gas leaks using vision-based models — especially in harsh outdoor environments with wind, rain, snow, and limited edge-device compute. He introduces a breakthrough approach called channel stacking, a method that captures gas movement using just three consecutive frames to dramatically improve detection accuracy while reducing computational load and false alarms.

The conversation goes beyond theory, offering a behind-the-scenes look at how AI models are trained, optimized, and deployed at the edge — and where the technology is headed next. From edge computing to large language models (LLMs) and object-level incident classification, this episode highlights how AI, blockchain, and verification are reshaping the future of global energy markets.

⚡ If you work in energy, AI, emissions monitoring, or industrial technology, this episode is a must-listen.

⏱️ Episode Chapters

00:00 – Introduction to The Empirical Energy Podcast

00:57 – Meet the Guest: Jae Yoon Chung from Clean Connect

01:39 – Machine Learning Challenges in Energy Environments

03:44 – Innovations in Visual Gas Leak Detection

07:29 – Technical Deep Dive: Channel Stacking Explained

14:23 – The Future of Visual AI & LLM Integration

18:53 – Final Thoughts & Call to Action

🎧 Listen & Watch

▶️ YouTube: https://youtu.be/WOejlQSdr_g

🎙 Apple Podcasts: https://podcasts.apple.com/us/podcast/the-empirical-energy-podcast/id1822839881

💬 If this episode sparked new ideas or questions, join the conversation.

👉 Subscribe, rate the show, and share this episode with someone working in energy, AI, or climate tech.

👉 Drop a comment and tell us: Where do you see the biggest opportunity for AI in energy today?

#EmpiricalEnergyPodcast #VisualAI #MethaneDetection

#MachineLearning #EdgeAI #EnergyTech

#ClimateTech #IndustrialAI #ComputerVision